Making machines understand
Making machines understand
Natural language understanding technologies involves the identiﬁcation of the intended semantic from the multiple possible semantics. This means that the system needs a contextual lexicon of the language, with a suitable ontology, in order to provide to machines a mental model of the surrounding world and be able to assess the provided data to extract his meaning, in several languages and without prior training (no machine learning). This contextual ontological lexicon is then added to a categorized symbolic object structure, so that machines can better understand, be smarter and able to replicate the way humans understand.
With Percipion, organizations can analyze a large amount of data, content, and unstructured sources, such as product reviews, responses to surveys and polls, or social media posts and accurately extract information to get a full comprehension (deep meaning), including contextual nuances, identifying intentions and revealing mental states. Percipion helps make sense of this information that would otherwise require human intervention to be truly understood.
Percipion is able to understand a text, identify and evaluate sentiments (3 positives, 1 neutral, 3 negatives), emotions (8 primary, 24 secondary), human needs (13 primary, 27 secondary), positive and negative affective states, 3 types of intrinsic motivations, 2 types of extrinsic motivations and 7 different social competencies (general communication, verbal communication, non-verbal communication, leadership, influence, emotional intelligence and creativity). In addition, Percipion can be adapted to a business use case in order to evaluate a specific semantic context
Built on a new generation of analog computing methods using fuzzy logic and ontologies, Percipion is empowering organizations to conduct advanced assessments on their enterprise data in order to reveal new key insights related to the business context and/or linked to core mental states.
A positive technology
Percipion is a positive technology which will help people.
More than four years of research and development were necessary to create Percipion and meet the many current technological requirements and constraints.
Nowadays, it is important that natural language understanding technologies operate transparently, explain what they do, exploit useful and qualified data, have real-time analysis capacity and consume the least amount of energy. And that’s exactly what we did.
Your benefits using Percipion
Here is how Percipion works. In this example, we asked Percipion to analyze a political speech written in French (22,122 characters, 3,436 words) in order to reveal emotions.
In this example, Percipion is executed in a very specific mode that allows to follow the way in which it performs its semantic analysis (in accordance with future regulations on transparency of artificial intelligent solutions).
If you want to receive news from MacAnima about our software solutions, use cases or our success stories, please share with us your contact details